library(tidyverse) # data manipulation
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──
## ✓ ggplot2 3.3.3 ✓ purrr 0.3.4
## ✓ tibble 3.0.6 ✓ dplyr 1.0.4
## ✓ tidyr 1.1.2 ✓ stringr 1.4.0
## ✓ readr 1.4.0 ✓ forcats 0.5.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(cluster) # clustering algorithms
library(factoextra) # clustering algorithms & visualization
## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa
# Demo data
dataFrame <- data.frame(
row.names = c("PopRock", "RnB", "Electronics", "AvantGarde", "Blues", "Children", "Classical", "ComedySpoken", "Country", "EasyListening", "Folk", "International", "Jazz", "Latin", "NewAge", "Reggae", "Religious", "StageNScreen", "Vocals"),
danceability= c(0.51104,
0.621307,
0.58697,
0.55542,
0.569593,
0.684094,
0.336415,
0.555449,
0.585404,
0.447982,
0.528089,
0.563343,
0.516395,
0.626992,
0.373497,
0.704057,
0.540279,
0.290541,
0.457029
),
energy = c(0.6468,
0.546589,
0.63980,
0.28162,
0.439803,
0.432585,
0.180278,
0.554109,
0.495096,
0.345165,
0.273193,
0.433363,
0.333980,
0.595547,
0.206824,
0.514850,
0.603603,
0.235655,
0.253629
),
valence = c(0.55538,
0.615532,
0.427237,
0.490805,
0.652932,
0.706491,
0.328726,
0.471772,
0.599310,
0.421182,
0.517992,
0.651033,
0.489697,
0.690958,
0.217313,
0.717875,
0.465337,
0.203338,
0.426028
),
tempo = c(123.14705,
116.758008,
119.344773,
114.562697,
117.491006,
121.143491,
106.366333,
104.896751,
119.640495,
112.326550,
115.630660,
116.339237,
113.060721,
120.644974,
110.961211,
116.501575,
120.617865,
103.098356,
109.831115
),
loudness = c(-9.20412,
-9.800735,
-9.782777,
-14.338054,
-11.498389,
-9.558302,
-19.667728,
-14.207246,
-10.609901,
-14.522501,
-15.200286,
-11.566676,
-14.624186,
-8.626783,
-18.779600,
-10.431030,
-7.978997,
-17.889201,
-13.698602
),
mode = c(0.73970,
0.629490,
0.555932,
0.619910,
0.777985,
0.867925,
0.758907,
0.778816,
0.928174,
0.696154,
0.794603,
0.672479,
0.580040,
0.675282,
0.686792,
0.647761,
0.810370,
0.682016,
0.710580
),
key = c(5.1805658,
5.344163,
5.455933,
5.466063,
5.034515,
4.377358,
4.884334,
5.127726,
5.342288,
4.870513,
5.149925,
5.122820,
4.905347,
5.227634,
4.513208,
5.673134,
5.226667,
4.834926,
5.258562
),
acousticness = c(0.25420,
0.359069,
0.231992,
0.738263,
0.634420,
0.660398,
0.940046,
0.794572,
0.469606,
0.698889,
0.760548,
0.701630,
0.729896,
0.441365,
0.854203,
0.295487,
0.340366,
0.774718,
0.820661
),
instrumentalness = c(0.09241,
0.036275,
0.383143,
0.149248,
0.084210,
0.009765,
0.518732,
0.003496,
0.035471,
0.527300,
0.071377,
0.169907,
0.396698,
0.044371,
0.719714,
0.098852,
0.013442,
0.568359,
0.021624
),
liveness = c(0.21617,
0.194166,
0.200414,
0.173906,
0.205921,
0.273757,
0.194257,
0.611077,
0.185207,
0.168208,
0.184784,
0.207664,
0.186170,
0.184466,
0.145138,
0.198535,
0.244273,
0.173066,
0.211890
),
speechiness = c(0.05903,
0.073552,
0.077413,
0.059323,
0.065374,
0.088896,
0.065237,
0.658424,
0.045802,
0.045504,
0.064941,
0.092366,
0.055622,
0.060981,
0.045157,
0.133643,
0.063291,
0.060431,
0.058829
),
explicit = c(0.04573,
0.092887,
0.076271,
0.000000,
0.001866,
0.000000,
0.000000,
0.208723,
0.003619,
0.000000,
0.000750,
0.025777,
0.000664,
0.016567,
0.000000,
0.021642,
0.000000,
0.000000,
0.000000
),
duration_ms = c(239916.5017,
246655.829,
284212.461,
211989.579186,
214966.204291,
129214.679245,
291495.821864,
219118.591900,
195926.202533,
174263.412821,
196734.868066,
265348.237301,
303131.455829,
228668.884029,
291237.694340,
241206.968657,
263544.971852,
217302.643788,
188957.381146
),
popularity = c(40.92764,
39.145475,
49.548305,
23.009050,
22.248134,
22.698113,
12.382138,
21.869159,
35.641286,
18.833333,
24.091454,
19.598939,
20.853703,
44.378728,
37.286792,
36.302239,
41.890370,
32.215465,
20.364869
))
normalize <- function(x) {
return ((x - min(x)) / (max(x) - min(x))) }
dataFrame$tempo <- normalize(dataFrame$tempo)
dataFrame$duration_ms <- normalize(dataFrame$duration_ms)
dataFrame$loudness <- normalize(dataFrame$loudness)
dataFrame$mode <- normalize(dataFrame$mode)
dataFrame$key <- normalize(dataFrame$key)
dataFrame$popularity <- normalize(dataFrame$popularity)
library(fmsb)
max_min <- data.frame(
danceability = c(1, 0), energy = c(1, 0),
valence = c(1, 0), tempo = c(1, 0), loudness = c(1, 0),
mode = c(1, 0), key = c(1, 0), acousticness = c(1, 0), instrumentalness = c(1,0), liveness = c(1,0), speechiness = c(1,0), explicit = c(1,0), duration_ms = c(1,0), popularity = c(1,0)
)
rownames(max_min) <- c("Max", "Min")
# Bind the variable ranges to the data
df <- rbind(max_min, dataFrame)
df
# Plot the data for Pop/Rock
library(fmsb)
PopRock<- df[c("Max", "Min", "PopRock"), ]
radarchart(PopRock)
# Plot the data for R&B
library(fmsb)
RnB <- df[c("Max", "Min", "RnB"), ]
radarchart(RnB)
# Plot the data for Electronics
library(fmsb)
Electronics <- df[c("Max", "Min", "Electronics"), ]
radarchart(Electronics)
# Plot the data for Avant-Garde
library(fmsb)
AvantGarde <- df[c("Max", "Min", "AvantGarde"), ]
radarchart(AvantGarde)
# Plot the data for Blues
library(fmsb)
Blues <- df[c("Max", "Min", "Blues"), ]
radarchart(Blues)
# Plot the data for Children
library(fmsb)
Children<- df[c("Max", "Min", "Children"), ]
radarchart(Children)
# Plot the data for Classical
library(fmsb)
Classical <- df[c("Max", "Min", "Classical"), ]
radarchart(Classical)
# Plot the data for ComedySpoken
library(fmsb)
ComedySpoken <- df[c("Max", "Min", "ComedySpoken"), ]
radarchart(ComedySpoken)
# Plot the data for Country
library(fmsb)
Country<- df[c("Max", "Min", "Country"), ]
radarchart(Country)
# Plot the data for Easy Lisenting
library(fmsb)
EasyListening<- df[c("Max", "Min", "EasyListening"), ]
radarchart(EasyListening)
# Plot the data for Folk
library(fmsb)
Folk<- df[c("Max", "Min", "Folk"), ]
radarchart(Folk)
# Plot the data for International
library(fmsb)
International<- df[c("Max", "Min", "International"), ]
radarchart(International)
# Plot the data for Jazz
library(fmsb)
Jazz<- df[c("Max", "Min", "Jazz"), ]
radarchart(Jazz)
# Plot the data for Latin
library(fmsb)
Latin<- df[c("Max", "Min", "Latin"), ]
radarchart(Latin)
# Plot the data for New Age
library(fmsb)
NewAge<- df[c("Max", "Min", "NewAge"), ]
radarchart(NewAge)
# Plot the data for Reggae
library(fmsb)
Reggae<- df[c("Max", "Min", "Reggae"), ]
radarchart(Reggae)
# Plot the data for Religious
library(fmsb)
Religious<- df[c("Max", "Min", "Religious"), ]
radarchart(Religious)
# Plot the data for StageNScreen
library(fmsb)
StageNScreen<- df[c("Max", "Min", "StageNScreen"), ]
radarchart(StageNScreen)
# Plot the data for Vocals
library(fmsb)
Vocals<- df[c("Max", "Min", "Vocals"), ]
radarchart(Vocals)
create_beautiful_radarchart <- function(data, color = "#00AFBB",
vlabels = colnames(data), vlcex = 0.7,
caxislabels = NULL, title = NULL, ...){
radarchart(
data, axistype = 1,
# Customize the polygon
pcol = color, pfcol = scales::alpha(color, 0.5), plwd = 2, plty = 1,
# Customize the grid
cglcol = "grey", cglty = 1, cglwd = 0.8,
# Customize the axis
axislabcol = "grey",
# Variable labels
vlcex = vlcex, vlabels = vlabels,
caxislabels = caxislabels, title = title, ...
)
}
# Reduce plot margin using par()
op <- par(mar = c(1, 2, 2, 2))
# Create the radar charts
create_beautiful_radarchart(
data = df, caxislabels = c(0, 5, 10, 15, 20),
color = c("#00AFBB", "#E7B800", "#FC4E07", "#33FF5B", "#9755F7", "#F9F63D", "#3DF9BA", "#F57527")
)
# Add an horizontal legend
legend(
x = "bottom", legend = rownames(df[-c(1,2),]), horiz = TRUE,
bty = "n", pch = 20 , col = c("#00AFBB", "#E7B800", "#FC4E07", "#33FF5B", "#9755F7", "#F9F63D", "#3DF9BA", "#F57527"),
text.col = "black", cex = 0.5, pt.cex = 1.5
)
par(op)
library(fmsb)
max_min <- data.frame(
danceability = c(1, 0), energy = c(1, 0),
valence = c(1, 0), tempo = c(1, 0), loudness = c(1, 0),
mode = c(1, 0), key = c(1, 0), acousticness = c(1, 0), instrumentalness = c(1,0), liveness = c(1,0), speechiness = c(1,0), explicit = c(1,0), duration_ms = c(1,0), popularity = c(1,0)
)
rownames(max_min) <- c("Max", "Min")
# Bind the variable ranges to the data
df <- rbind(max_min, dataFrame)
df
dataFrame
df2 <- t(dataFrame) %>%
as.data.frame() %>%
rownames_to_column("Field")
df2
library(tidyverse)
library(ggpubr)
ggdotchart(
df2, x = "Field", y = "PopRock",
add = "segments", sorting = "descending",
ylab = "Values", title = "PopRock"
)
library(scales)
##
## Attaching package: 'scales'
## The following object is masked from 'package:purrr':
##
## discard
## The following object is masked from 'package:readr':
##
## col_factor
df_scaled <- round(apply(df, 2, scales::rescale), 2)
df_scaled <- as.data.frame(df_scaled)
head(df_scaled)
# Variables summary
# Get the minimum and the max of every column
col_max <- apply(df_scaled, 2, max)
col_min <- apply(df_scaled, 2, min)
# Calculate the average profile
col_mean <- apply(df_scaled, 2, mean)
# Put together the summary of columns
col_summary <- t(data.frame(Max = col_max, Min = col_min, Average = col_mean))
# Bind variables summary to the data
df_scaled2 <- as.data.frame(rbind(col_summary, df_scaled))
head(df_scaled2)
opar <- par()
# Define settings for plotting in a 3x4 grid, with appropriate margins:
par(mar = rep(0.8,4))
par(mfrow = c(2,4))
# Produce a radar-chart for each student
for (i in 6:nrow(df_scaled2)) {
radarchart(
df_scaled2[c(1:3, i), ],
pfcol = c("#99999980",NA),
pcol= c(NA,2), plty = 1, plwd = 2,
title = row.names(df_scaled2)[i]
)
}
# Restore the standard par() settings
par <- par(opar)
## Warning in par(opar): graphical parameter "cin" cannot be set
## Warning in par(opar): graphical parameter "cra" cannot be set
## Warning in par(opar): graphical parameter "csi" cannot be set
## Warning in par(opar): graphical parameter "cxy" cannot be set
## Warning in par(opar): graphical parameter "din" cannot be set
## Warning in par(opar): graphical parameter "page" cannot be set
# create a word cloud
script <- "http://www.sthda.com/upload/rquery_wordcloud.r"
source(script)
res<-rquery.wordcloud("/Users/aniketsingh/Desktop/music/JFKspeech.txt",
type ="file",
lang = "english")
## Loading required package: NLP
##
## Attaching package: 'NLP'
## The following object is masked from 'package:ggplot2':
##
## annotate
## Loading required package: RColorBrewer
## Warning in readLines(x): incomplete final line found on '/Users/aniketsingh/
## Desktop/music/JFKspeech.txt'
## Warning in tm_map.SimpleCorpus(docs, content_transformer(tolower)):
## transformation drops documents
## Warning in tm_map.SimpleCorpus(docs, removeNumbers): transformation drops
## documents
## Warning in tm_map.SimpleCorpus(docs, removeWords, stopwords(lang)):
## transformation drops documents
## Warning in tm_map.SimpleCorpus(docs, removePunctuation): transformation drops
## documents
## Warning in tm_map.SimpleCorpus(docs, stripWhitespace): transformation drops
## documents
